Active object localization with deep reinforcement learning

Juan C. Caicedo, Svetlana Lazebnik

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present an active detection model for localizing objects in scenes. The model is class-specific and allows an agent to focus attention on candidate regions for identifying the correct location of a target object. This agent learns to deform a bounding box using simple transformation actions, with the goal of determining the most specific location of target objects following top-down reasoning. The proposed localization agent is trained using deep reinforcement learning, and evaluated on the Pascal VOC 2007 dataset. We show that agents guided by the proposed model are able to localize a single instance of an object after analyzing only between 11 and 25 regions in an image, and obtain the best detection results among systems that do not use object proposals for object localization.

Original languageEnglish (US)
Title of host publication2015 International Conference on Computer Vision, ICCV 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2488-2496
Number of pages9
ISBN (Electronic)9781467383912
DOIs
StatePublished - Feb 17 2015
Event15th IEEE International Conference on Computer Vision, ICCV 2015 - Santiago, Chile
Duration: Dec 11 2015Dec 18 2015

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2015 International Conference on Computer Vision, ICCV 2015
ISSN (Print)1550-5499

Other

Other15th IEEE International Conference on Computer Vision, ICCV 2015
CountryChile
CitySantiago
Period12/11/1512/18/15

Fingerprint

Reinforcement learning
Volatile organic compounds

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Caicedo, J. C., & Lazebnik, S. (2015). Active object localization with deep reinforcement learning. In 2015 International Conference on Computer Vision, ICCV 2015 (pp. 2488-2496). [7410643] (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2015 International Conference on Computer Vision, ICCV 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2015.286

Active object localization with deep reinforcement learning. / Caicedo, Juan C.; Lazebnik, Svetlana.

2015 International Conference on Computer Vision, ICCV 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 2488-2496 7410643 (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2015 International Conference on Computer Vision, ICCV 2015).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Caicedo, JC & Lazebnik, S 2015, Active object localization with deep reinforcement learning. in 2015 International Conference on Computer Vision, ICCV 2015., 7410643, Proceedings of the IEEE International Conference on Computer Vision, vol. 2015 International Conference on Computer Vision, ICCV 2015, Institute of Electrical and Electronics Engineers Inc., pp. 2488-2496, 15th IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, 12/11/15. https://doi.org/10.1109/ICCV.2015.286
Caicedo JC, Lazebnik S. Active object localization with deep reinforcement learning. In 2015 International Conference on Computer Vision, ICCV 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 2488-2496. 7410643. (Proceedings of the IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2015.286
Caicedo, Juan C. ; Lazebnik, Svetlana. / Active object localization with deep reinforcement learning. 2015 International Conference on Computer Vision, ICCV 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 2488-2496 (Proceedings of the IEEE International Conference on Computer Vision).
@inproceedings{8e102d3b108246bdbf44b016d8121fd7,
title = "Active object localization with deep reinforcement learning",
abstract = "We present an active detection model for localizing objects in scenes. The model is class-specific and allows an agent to focus attention on candidate regions for identifying the correct location of a target object. This agent learns to deform a bounding box using simple transformation actions, with the goal of determining the most specific location of target objects following top-down reasoning. The proposed localization agent is trained using deep reinforcement learning, and evaluated on the Pascal VOC 2007 dataset. We show that agents guided by the proposed model are able to localize a single instance of an object after analyzing only between 11 and 25 regions in an image, and obtain the best detection results among systems that do not use object proposals for object localization.",
author = "Caicedo, {Juan C.} and Svetlana Lazebnik",
year = "2015",
month = "2",
day = "17",
doi = "10.1109/ICCV.2015.286",
language = "English (US)",
series = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2488--2496",
booktitle = "2015 International Conference on Computer Vision, ICCV 2015",
address = "United States",

}

TY - GEN

T1 - Active object localization with deep reinforcement learning

AU - Caicedo, Juan C.

AU - Lazebnik, Svetlana

PY - 2015/2/17

Y1 - 2015/2/17

N2 - We present an active detection model for localizing objects in scenes. The model is class-specific and allows an agent to focus attention on candidate regions for identifying the correct location of a target object. This agent learns to deform a bounding box using simple transformation actions, with the goal of determining the most specific location of target objects following top-down reasoning. The proposed localization agent is trained using deep reinforcement learning, and evaluated on the Pascal VOC 2007 dataset. We show that agents guided by the proposed model are able to localize a single instance of an object after analyzing only between 11 and 25 regions in an image, and obtain the best detection results among systems that do not use object proposals for object localization.

AB - We present an active detection model for localizing objects in scenes. The model is class-specific and allows an agent to focus attention on candidate regions for identifying the correct location of a target object. This agent learns to deform a bounding box using simple transformation actions, with the goal of determining the most specific location of target objects following top-down reasoning. The proposed localization agent is trained using deep reinforcement learning, and evaluated on the Pascal VOC 2007 dataset. We show that agents guided by the proposed model are able to localize a single instance of an object after analyzing only between 11 and 25 regions in an image, and obtain the best detection results among systems that do not use object proposals for object localization.

UR - http://www.scopus.com/inward/record.url?scp=84973897631&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973897631&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2015.286

DO - 10.1109/ICCV.2015.286

M3 - Conference contribution

AN - SCOPUS:84973897631

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 2488

EP - 2496

BT - 2015 International Conference on Computer Vision, ICCV 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -